APEX
Leaderboard
Models
Compare
Tasks
Metrics
About
Leaderboard
Overall
Frontend
Backend
Full-Stack
Debugging
Refactoring
Code Review
From Scratch
Multi-Language
All Levels
Easy
Medium
Hard
Expert
Master
#
Model
ELO
Peak
Avg Score
Avg Cost
Consistency
1
Claude Opus 4.6
1840
1854
84.8
$0.89
98.5%
2
Claude Sonnet 4.6
1839
1851
84.2
$0.24
93.8%
3
GPT 5.2
1828
1833
80.0
$0.31
82.8%
4
GPT 5.3 Codex
1808
1839
80.2
$0.28
82.8%
5
Claude Opus 4.5
1783
1794
82.6
$0.70
93.8%
6
GPT 5.2 Codex
1753
1772
78.0
$0.18
77.0%
7
GPT 5.1 Codex Mini
1747
1765
81.0
$1.80
93.3%
8
Gemini 3.1 Pro Preview
1672
1676
75.7
$0.57
69.3%
9
Gemini 3 Pro Preview
1641
1665
74.9
$0.46
72.3%
10
GLM 5
1632
1642
73.1
$0.15
69.4%
11
Claude Sonnet 4.5
1625
1661
75.5
$0.25
71.0%
12
Grok 4
1594
1610
71.5
$0.27
66.9%
13
Kimi K2.5
1590
1603
72.1
$0.13
68.0%
14
Gemini 2.5 Pro
1575
1595
67.9
$0.27
52.6%
15
GLM 4.7
1574
1588
71.5
$0.10
64.5%
16
Qwen3.5 27b
1573
1584
70.0
$0.32
59.8%
17
Grok 4.1 Fast
1570
1601
68.3
$0.05
60.2%
18
Qwen3.5 122b A10b
1564
1574
69.2
$0.38
57.3%
19
Claude Haiku 4.5
1553
1557
71.1
$0.07
61.5%
20
Qwen3.5 397b A17b
1549
1558
68.0
$0.12
54.5%
21
Gemini 3 Flash Preview
1544
1559
72.0
$0.02
65.2%
22
Qwen3.5 122b A10b [Q4_K_XL]
1541
1541
70.9
$0.24
60.2%
23
Qwen3.5 Plus 02.15
1511
1534
58.1
$0.10
40.0%
24
GLM 4.7 [Q4_K_XL]
1507
1526
70.6
$0.04
51.2%
25
Minimax M2.1
1475
1477
64.8
$0.12
46.4%
26
Grok Code Fast 1
1473
1486
65.6
$0.07
42.4%
27
Step 3.5 Flash
1472
1496
53.7
$0.14
37.7%
28
Qwen3.5 27b [Q4_K_M]
1468
1481
62.8
$0.18
42.7%
29
Qwen3.5 Flash 02.23
1453
1464
63.2
$0.06
46.3%
30
Minimax M2.5
1453
1471
63.4
$0.14
42.3%
31
GLM 4.5
1448
1464
65.2
$0.10
48.6%
32
Deepseek R1 0528
1445
1446
64.2
$0.05
42.7%
33
Qwen3.5 35b A3b
1445
1456
63.4
$0.08
43.0%
34
GLM 4.6
1441
1451
64.1
$0.11
40.7%
35
Qwen3 Coder Plus
1420
1428
62.8
$0.12
39.3%
36
Qwen3 Coder
1417
1427
60.6
$0.11
37.8%
37
Deepseek V3.2
1414
1416
63.8
$0.14
37.5%
38
Devstral 2512
1400
1412
62.8
$0.10
32.4%
39
Minimax M2.5 [Q4_K_XL]
1395
1416
63.6
$0.03
33.3%
40
Qwen3 Coder Next
1388
1399
60.9
$0.11
36.1%
41
GPT OSS 120b
1378
1384
58.9
$0.12
30.2%
42
GLM 4.5 Air
1361
1388
59.9
$0.03
29.1%
43
Qwen3 Coder Flash
1344
1367
58.8
$0.09
27.5%
44
Qwen3 Coder Next [Q4_K_XL]
1303
1319
57.6
$0.01
19.5%
45
GLM 4.7 Flash
1299
1315
55.4
$0.01
22.4%
46
Trinity Large Preview:free
1292
1297
51.3
$0.05
19.6%
47
GPT OSS 20b
1265
1270
53.3
$0.11
21.9%
48
Nemotron 3 Nano 30b A3b
1241
1258
52.0
$0.09
18.3%
49
Qwen3.5 35b A3b [Q4_K_XL]
1240
1286
40.5
$0.05
13.4%
50
Gemini 2.5 Flash Lite
1201
1210
52.9
$0.02
13.5%
51
Qwen3 Coder 30b [Q4_K_M]
1153
1181
51.8
$0.01
12.5%
ELO Distribution